Jared Coleman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jared Coleman has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Bhaskar Krishnamachari
Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA
8 shared publications - Oscar Morales-Ponce
California State University Long Beach USA
7 shared publications - Danny Krizanc
Wesleyan University
4 shared publications - Evangelos Kranakis
Carleton University, Ottawa, Ontario, Canada
4 shared publications Danny Krizanc
3 shared publications- Dmitry Ivanov
Carleton University
3 shared publications
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 243-262
Evaluating the Impact of Algorithmic Components on Task Graph Scheduling
- 2 January 2026
- Published by Springer Nature
- p. 243-262
Evaluating the Impact of Algorithmic Components on Task Graph Scheduling
- Open Access
- 8 December 2025
- Published by Elsevier in Journal of Computer and System Sciences
- Vol. 157
The power of knowledge in linear search for an escaping target
- 8 December 2025
- Published by Elsevier in Journal of Computer and System Sciences
- Vol. 157
Open AccessThe power of knowledge in linear search for an escaping target
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2169-2180
Adapting Classic Scheduling Heuristics for Online Execution under Uncertainty
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2169-2180
Open AccessAdapting Classic Scheduling Heuristics for Online Execution under Uncertainty
- 18 July 2025
- Published by Springer Nature
- p. 433-445
Linear Search with Probabilistic Detection and Variable Speeds
- 18 July 2025
- Published by Springer Nature
- p. 433-445
Linear Search with Probabilistic Detection and Variable Speeds
- Open Access
Crowd-SFT: Crowdsourcing for LLM Alignment
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT without extensive annotator training. Our framework promotes incentive fairness via a point-based reward system correlated with Shapley values and guides model convergence through iterative model updates. Our multi-model selection framework demonstrates up to a 55% reduction in target distance over single-model selection, enabling subsequent experiments that validate our point-based reward mechanism's close alignment with Shapley values (a well-established method for attributing individual contributions) thereby supporting fair and scalable participation.
Open AccessCrowd-SFT: Crowdsourcing for LLM Alignment
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT without extensive annotator training. Our framework promotes incentive fairness via a point-based reward system correlated with Shapley values and guides model convergence through iterative model updates. Our multi-model selection framework demonstrates up to a 55% reduction in target distance over single-model selection, enabling subsequent experiments that validate our point-based reward mechanism's close alignment with Shapley values (a well-established method for attributing individual contributions) thereby supporting fair and scalable participation.
- Open Access
Linear Search with Probabilistic Detection and Variable Speeds
We present results on new variants of the famous linear search (or cow-path) problem that involves an agent searching for a target with unknown position on the infinite line. We consider the variant where the agent can move either at speed $1$ or at a slower speed $v \in [0, 1)$. When traveling at the slower speed $v$, the agent is guaranteed to detect the target upon passing through its location. When traveling at speed $1$, however, the agent, upon passing through the target's location, detects it with probability $p \in [0, 1]$. We present algorithms and provide upper bounds for the competitive ratios for three cases separately: when $p=0$, $v=0$, and when $p,v \in (0,1)$. We also prove that the provided algorithm for the $p=0$ case is optimal.Open AccessLinear Search with Probabilistic Detection and Variable Speeds
We present results on new variants of the famous linear search (or cow-path) problem that involves an agent searching for a target with unknown position on the infinite line. We consider the variant where the agent can move either at speed $1$ or at a slower speed $v \in [0, 1)$. When traveling at the slower speed $v$, the agent is guaranteed to detect the target upon passing through its location. When traveling at speed $1$, however, the agent, upon passing through the target's location, detects it with probability $p \in [0, 1]$. We present algorithms and provide upper bounds for the competitive ratios for three cases separately: when $p=0$, $v=0$, and when $p,v \in (0,1)$. We also prove that the provided algorithm for the $p=0$ case is optimal. - Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 624-625
Poster Abstract: Scheduling Dynamic IoT Task Graphs
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 624-625
Open AccessPoster Abstract: Scheduling Dynamic IoT Task Graphs
- Open Access
- 1 January 2025
- Published by Loyola Marymount University
Community Voices on Digital Tools for Owens Valley Paiute
This report presents findings from a two-week online survey of Owens Valley Paiute community members and affiliates on their perspectives toward digital tools for language revitalization. A total of 36 respondents participated, most identifying as beginners in the Owens Valley Paiute language. The survey explored barriers to learning, such as limited time, insufficient materials, and uncertainty about where to begin, alongside community interest in digital support. Respondents expressed strong enthusiasm for language games, sentence-building guidance, self-paced courses, and translation tools. Qualitative feedback highlighted the importance of trust, privacy, cultural oversight, and community control in the development of digital resources. The report concludes with implications for community-led, culturally grounded approaches to leveraging technology in language revitalization.
- 1 January 2025
- Published by Loyola Marymount University
Open AccessCommunity Voices on Digital Tools for Owens Valley Paiute
This report presents findings from a two-week online survey of Owens Valley Paiute community members and affiliates on their perspectives toward digital tools for language revitalization. A total of 36 respondents participated, most identifying as beginners in the Owens Valley Paiute language. The survey explored barriers to learning, such as limited time, insufficient materials, and uncertainty about where to begin, alongside community interest in digital support. Respondents expressed strong enthusiasm for language games, sentence-building guidance, self-paced courses, and translation tools. Qualitative feedback highlighted the importance of trust, privacy, cultural oversight, and community control in the development of digital resources. The report concludes with implications for community-led, culturally grounded approaches to leveraging technology in language revitalization.
- 22 June 2024
- Published by Springer Nature
- p. 396-407
Linear Search for an Escaping Target with Unknown Speed
- 22 June 2024
- Published by Springer Nature
- p. 396-407
Linear Search for an Escaping Target with Unknown Speed